Insights into Depression Through Advanced Neuroimaging Techniques
Gereon J. Schnellbächer, Ravichandran Rajkumar, Tanja Veselinović, Shukti Ramkiran, Jana Hagen, Maria Collee, N. Jon Shah and Irene Neuner
29th November 2024
A recent INM-4 study has leveraged ultra-high field strength MRI (7T) and machine learning methods to explore structural brain changes in individuals with major depressive disorder (MDD). The research involved imaging the brains of 41 patients with MDD and 41 healthy controls using a 7-Tesla MRI, focusing on the default-mode network (DMN) and examining features like grey matter volume (GMV) and gyrification.
Analysis revealed that gyrification data enabled a predictive accuracy of 76% for identifying MDD through support vector machine analysis. While GMV changes in the left parahippocampal gyrus were found to correlate with depression severity, GMV was not reliable for predicting the presence of MDD. Cortical thickness did not show significant relevance in a preliminary statistical investigation and was excluded from further analysis.
The study suggests that DMN structural features may help identify MDD, though challenges remain in predicting disease progression or treatment response due to variability in GMV and the static nature of gyrification. Further advances in imaging and analytical techniques could address these limitations and improve understanding of MDD.
Original Publication: Structural alterations as a predictor of depression – a 7-Tesla MRI-based multidimensional approach